推荐[ For iPhone / iPad ] 🔥 惊艳！苹果交互式壁纸，让你的桌面动起来

skills.homescapability registry 搜索

查询中

搜索技能

为您的 Agent 寻找最完美的能力。

热门搜索

python ai web scraper mcp pdf git docker typescript

结果数

53,183

符合搜索条件的技能

当前页

445

共 2660 页

关键词

ai

按名称、标签或描述搜索

knowledge-base

1.2K

dev-container-maintenance

Modify, audit, troubleshoot, and maintain the VS Code Dev Container setup for Open Mercato. MUST use this skill for ANY change to .devcontainer/ files — it contains the file map, update procedures, and mandatory documentation requirements. Use when: (1) adding or changing anything in the dev container (new system packages, new services, version bumps, Dockerfile edits, env var changes, port changes), (2) the dev container fails to build or start, (3) services inside the container misbehave (wrong versions, connection errors, missing env vars), (4) the regular project setup changed and the dev container needs to match, (5) a user reports "works locally but not in dev container", (6) periodic maintenance audit. Triggers on any mention of "dev container", "devcontainer", ".devcontainer", "container setup", "container Dockerfile", "add to container", "install in container", "update dev container", "container broken", "container not working".

open-mercato

documentation

knowledge-base

1.2K

troubleshooter

Diagnose and fix common issues in Open Mercato standalone apps. Use when encountering errors, unexpected behavior, modules not loading, widgets not appearing, migrations failing, build errors, or any "it doesn't work" situation. Triggers on "error", "not working", "broken", "fix", "debug", "why isn't", "can't", "fails", "crash", "missing", "404", "500", "module not found", "widget not showing".

open-mercato

documentation

technical-docs

1.2K

create-agents-md

Create or rewrite AGENTS.md files for Open Mercato packages and modules. Use this skill when adding a new package, creating a new module, or when an existing AGENTS.md needs to be created or refactored. Ensures prescriptive tone, MUST rules, checklists, and consistent structure across all agent guidelines.

open-mercato

documentation

technical-docs

1.2K

spec-writing

Guide for creating high-quality specifications for {{PROJECT_NAME}}. Use when starting a new SPEC or reviewing specs against architectural standards.

open-mercato

documentation

code-quality

1.2K

code-review

Review code changes for architecture, security, conventions, and quality compliance. Use when reviewing pull requests, code changes, or auditing code quality.

open-mercato

testing-security

testing

1.2K

check-and-commit

Verify that the Open Mercato app is ready to publish by running build, generation, i18n, typecheck, unit test, and app build checks; fix obvious i18n sync or usage issues; and if everything passes, commit and push the current branch. Use this skill when the user asks to check the branch, make CI-style verification pass, fix i18n drift, then commit and push.

open-mercato

testing-security

testing

1.2K

integration-tests

Run and create QA integration tests (Playwright TypeScript), including executing the full suite, converting optional markdown scenarios, and generating new tests from specs or feature descriptions. Use when the user says "run integration tests", "test this feature", "create test for", "convert test case", "run QA tests", or "integration test".

open-mercato

testing-security

data-engineering

1.2K

stable-diffusion-image-generation

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

math-inc

data-ai

data-engineering

1.2K

pinecone

Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.

math-inc

data-ai

machine-learning

1.2K

lambda-labs-gpu-cloud

Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.

math-inc

data-ai

machine-learning

1.2K

huggingface-tokenizers

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

math-inc

data-ai

machine-learning

1.2K

nemo-curator

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

math-inc

data-ai

machine-learning

1.2K

obliteratus

Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.

math-inc

data-ai

machine-learning

1.2K

clip

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

math-inc

data-ai

machine-learning

1.2K

axolotl

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

math-inc

data-ai

machine-learning

1.2K

grpo-rl-training

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

math-inc

data-ai

machine-learning

1.2K

peft-fine-tuning

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

math-inc

data-ai

machine-learning

1.2K

pytorch-fsdp

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

math-inc

data-ai

machine-learning

1.2K

simpo-training

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

math-inc

data-ai

machine-learning

1.2K

slime-rl-training

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

math-inc

data-ai

第 445 页 / 共 2660 页